Dense Depth from Event Focal Stack
This addresses depth estimation for event cameras, which is useful for robotics and vision applications, but it is incremental as it builds on existing event-based and depth-from-defocus methods.
The paper tackles dense depth estimation from event streams by sweeping the focal plane of an event camera, using a convolutional neural network trained on synthesized event focal stacks from Blender to infer depth maps, and it shows superior performance over a depth-from-defocus method on synthetic and real datasets.
We propose a method for dense depth estimation from an event stream generated when sweeping the focal plane of the driving lens attached to an event camera. In this method, a depth map is inferred from an ``event focal stack'' composed of the event stream using a convolutional neural network trained with synthesized event focal stacks. The synthesized event stream is created from a focal stack generated by Blender for any arbitrary 3D scene. This allows for training on scenes with diverse structures. Additionally, we explored methods to eliminate the domain gap between real event streams and synthetic event streams. Our method demonstrates superior performance over a depth-from-defocus method in the image domain on synthetic and real datasets.